【来自:http://www.cnblogs.com/denny402/p/5685909.html】
整个工作目录建在:/home/ubunt16041/caffe/examples/abc_mnist/
再建一个mnist目录,所有的都放在mnist目录下。
(/home/ubuntu16041/caffe/examples/abc_mnist/mnist/)
图片下载好,test.txt,train.txt都有了。
mnist.py用来生成训练需要的文件:
# -*- coding: utf-8 -*-
import caffe
from caffe import layers as L,params as P,proto,to_proto
#设定文件的保存路径
root='/home/ubuntu16041/caffe/examples/abc_mnist/' #根目录
train_list=root+'mnist/train/train.txt' #训练图片列表
test_list=root+'mnist/test/test.txt' #测试图片列表
train_proto=root+'mnist/train.prototxt' #训练配置文件
test_proto=root+'mnist/test.prototxt' #测试配置文件
solver_proto=root+'mnist/solver.prototxt' #参数文件
#编写一个函数,生成配置文件prototxt
def Lenet(img_list,batch_size,include_acc=False):
#第一层,数据输入层,以ImageData格式输入
data, label = L.ImageData(source=img_list, batch_size=batch_size, ntop=2,root_folder=root,
transform_param=dict(scale= 0.00390625))
#第二层:卷积层
conv1=L.Convolution(data, kernel_size=5, stride=1,num_output=20, pad=0,weight_filler=dict(type='xavier'))
#池化层
pool1=L.Pooling(conv1, pool=P.Pooling.MAX, kernel_size=2, stride=2)
#卷积层
conv2=L.Convolution(pool1, kernel_size=5, stride=1,num_output=50, pad=0,weight_filler=dict(type='xavier'))
#池化层
pool2=L.Pooling(conv2, pool=P.Pooling.MAX, kernel_size=2, stride=2)
#全连接层
fc3=L.InnerProduct(pool2, num_output=500,weight_filler=dict(type='xavier'))
#激活函数层
relu3=L.ReLU(fc3, in_place=True)
#全连接层
fc4 = L.InnerProduct(relu3, num_output=10,weight_filler=dict(type='xavier'))
#softmax层
loss = L.SoftmaxWithLoss(fc4, label)
if include_acc: # test阶段需要有accuracy层
acc = L.Accuracy(fc4, label)
return to_proto(loss, acc)
else:
return to_proto(loss)
def write_net():
#写入train.prototxt
with open(train_proto, 'w') as f:
f.write(str(Lenet(train_list,batch_size=64)))
#写入test.prototxt
with open(test_proto, 'w') as f:
f.write(str(Lenet(test_list,batch_size=100, include_acc=True)))
#编写一个函数,生成参数文件
def gen_solver(solver_file,train_net,test_net):
s=proto.caffe_pb2.SolverParameter()
s.train_net =train_net
s.test_net.append(test_net)
s.test_interval = 938 #60000/64,测试间隔参数:训练完一次所有的图片,进行一次测试
s.test_iter.append(500) #50000/100 测试迭代次数,需要迭代500次,才完成一次所有数据的测试
s.max_iter = 9380 #10 epochs , 938*10,最大训练次数
s.base_lr = 0.01 #基础学习率
s.momentum = 0.9 #动量
s.weight_decay = 5e-4 #权值衰减项
s.lr_policy = 'step' #学习率变化规则
s.stepsize=3000 #学习率变化频率
s.gamma = 0.1 #学习率变化指数
s.display = 20 #屏幕显示间隔
s.snapshot = 938 #保存caffemodel的间隔
s.snapshot_prefix = root+'mnist/lenet' #caffemodel前缀
s.type ='SGD' #优化算法
s.solver_mode = proto.caffe_pb2.SolverParameter.CPU #加速
#写入solver.prototxt
with open(solver_file, 'w') as f:
f.write(str(s))
#开始训练
def training(solver_proto):
solver = caffe.SGDSolver(solver_proto)
solver.solve()
#
if __name__ == '__main__':
write_net()
gen_solver(solver_proto,train_proto,test_proto)
training(solver_proto)
运行:python mnist.py
接下来就是生成deploy.prototxt文件:
deploy.py
# -*- coding: utf-8 -*-
from caffe import layers as L,params as P,to_proto
root='/home/ubuntu16041/caffe/examples/abc_mnist/'
deploy=root+'mnist/deploy.prototxt' #文件保存路径
def create_deploy():
#少了第一层,data层
conv1=L.Convolution(bottom='data', kernel_size=5, stride=1,num_output=20, pad=0,weight_filler=dict(type='xavier'))
pool1=L.Pooling(conv1, pool=P.Pooling.MAX, kernel_size=2, stride=2)
conv2=L.Convolution(pool1, kernel_size=5, stride=1,num_output=50, pad=0,weight_filler=dict(type='xavier'))
pool2=L.Pooling(conv2, pool=P.Pooling.MAX, kernel_size=2, stride=2)
fc3=L.InnerProduct(pool2, num_output=500,weight_filler=dict(type='xavier'))
relu3=L.ReLU(fc3, in_place=True)
fc4 = L.InnerProduct(relu3, num_output=10,weight_filler=dict(type='xavier'))
#最后没有accuracy层,但有一个Softmax层
prob=L.Softmax(fc4)
return to_proto(prob)
def write_deploy():
with open(deploy, 'w') as f:
f.write('name:"Lenet"\n')
f.write('input:"data"\n')
f.write('input_dim:1\n')
f.write('input_dim:3\n')
f.write('input_dim:28\n')
f.write('input_dim:28\n')
f.write(str(create_deploy()))
if __name__ == '__main__':
write_deploy()
照样运行,就可以生成了。
最后就是测试:test.py
1 #coding=utf-8 2 3 import caffe 4 import numpy as np 5 root='/home/ubuntu16041/caffe/examples/abc_mnist/' #根目录 6 deploy=root + 'mnist/deploy.prototxt' #deploy文件 7 caffe_model=root + 'mnist/lenet_iter_9380.caffemodel' #训练好的 caffemodel 8 img=root+'mnist/test/8/00061.png' #随机找的一张待测图片 9 labels_filename = root + 'mnist/test/labels.txt' #类别名称文件,将数字标签转换回类别名称 10 11 net = caffe.Net(deploy,caffe_model,caffe.TEST) #加载model和network 12 13 #图片预处理设置 14 transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape}) #设定图片的shape格式(1,3,28,28) 15 transformer.set_transpose('data', (2,0,1)) #改变维度的顺序,由原始图片(28,28,3)变为(3,28,28) 16 #transformer.set_mean('data', np.load(mean_file).mean(1).mean(1)) #减去均值,前面训练模型时没有减均值,这儿就不用 17 transformer.set_raw_scale('data', 255) # 缩放到【0,255】之间 18 transformer.set_channel_swap('data', (2,1,0)) #交换通道,将图片由RGB变为BGR 19 20 im=caffe.io.load_image(img) #加载图片 21 net.blobs['data'].data[...] = transformer.preprocess('data',im) #执行上面设置的图片预处理操作,并将图片载入到blob中 22 23 #执行测试 24 out = net.forward() 25 26 labels = np.loadtxt(labels_filename, str, delimiter='\t') #读取类别名称文件 27 prob= net.blobs['Softmax1'].data[0].flatten() #取出最后一层(Softmax)属于某个类别的概率值,并打印 28 print prob 29 order=prob.argsort()[-1] #将概率值排序,取出最大值所在的序号 30 print 'the class is:',labels[order] #将该序号转换成对应的类别名称,并打印